A speech synthesis method, an electronic device, and a storage medium

By extracting and updating the user's paralinguistic library, the problem of speech synthesis systems being unable to capture the user's paralinguistics is solved, resulting in more natural and human-like synthesized audio, and improving the user's freedom of expression and audio diversity.

CN119446113BActive Publication Date: 2026-07-07HUAWEI TECH CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUAWEI TECH CO LTD
Filing Date
2023-07-31
Publication Date
2026-07-07

Smart Images

  • Figure CN119446113B_ABST
    Figure CN119446113B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of artificial intelligence, and discloses a speech synthesis method, an electronic device and a storage medium. In the speech synthesis method, multiple sub-languages of a user are acquired from a recording audio of the user, and a sub-language library of the user is updated based on the multiple sub-languages of the user. When speech synthesis is performed, the updated sub-language library is used to convert to-be-converted text into synthesized audio that has user voice characteristics and contains user sub-language characteristics. In this way, the user sub-languages can be synthesized in the synthesized audio, and the naturalness and personification of the synthesized audio are improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Speech synthesis model training method and device, computer equipment and storage medium

    CN112951200A

  • Method and system for text-to-speech synthesis with personalized voice

    US20080235024A1

  • Controllable, natural paralinguistics for text to speech synthesis

    US20220406292A1